Update app.py

app.py

@@ -33,12 +33,12 @@ def generate_text(message, history, max_tokens=512, temperature=0.9, top_p=0.95)
     temp = ""
     input_texts = [llama_o1_template(message)]
     input_texts = [input_text.replace('<|end_of_text|>','') for input_text in input_texts]
-    print(f"input_texts[0]: {input_texts[0]}")
+    #print(f"input_texts[0]: {input_texts[0]}")
     inputs = model.tokenize(input_texts[0].encode('utf-8'))
     for token in model.generate(inputs, top_p=top_p, temp=temperature):
-        print(f"token: {token}")
+        #print(f"token: {token}")
         text = model.detokenize([token])
-        print(f"text detok: {text}")
+        #print(f"text detok: {text}")
         temp += text.decode('utf-8')
         yield temp